Workflow commands help you break a big job into smaller steps. Each step is stored in its own file. An AI agent reads one step at a time. This keeps the agent focused and not overloaded with too much information at once.
You create a main command that lists the steps. The main command stays short and simple. The detailed instructions live in separate task files. The AI agent loads each task file only when it needs to do that step. This method is called context isolation.
Anyone who builds AI agents can use this skill. It makes complex tasks easier to manage. The agents stay on track and finish each step correctly. You save time and avoid messy instructions.
Global
mkdir -p ~/.claude/skills/create-workflow-commandProject
mkdir -p .claude/skills/create-workflow-commandSource Repository
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Triagemattpocock/skills
Triage issues with a state machine driven by clear roles and agent briefs
Handoffmattpocock/skills
Hand off your work to another AI agent with a clear summary
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly